Auto-Slides: An Interactive Multi-Agent System for Creating and Customizing Research Presentations
This addresses the challenge of systematic understanding and engagement with complex concepts for learners in education, though it is incremental as it builds on existing LLM capabilities for a specific application.
The authors tackled the problem of learners struggling with unstructured text-based interactions with research papers by proposing Auto-Slides, an LLM-driven system that converts papers into pedagogically structured, multimodal slides, resulting in strong learner acceptance, improved structural support for understanding, and expert-validated gains in narrative quality compared to conventional LLM-based reading.
The rapid progress of large language models (LLMs) has opened new opportunities for education. While learners can interact with academic papers through LLM-powered dialogue, limitations still exist: the lack of structured organization and the heavy reliance on text can impede systematic understanding and engagement with complex concepts. To address these challenges, we propose Auto-Slides, an LLM-driven system that converts research papers into pedagogically structured, multimodal slides (e.g., diagrams and tables). Drawing on cognitive science, it creates a presentation-oriented narrative and allows iterative refinement via an interactive editor to better match learners' knowledge level and goals. Auto-Slides further incorporates verification and knowledge retrieval mechanisms to ensure accuracy and contextual completeness. Through extensive user studies, Auto-Slides demonstrates strong learner acceptance, improved structural support for understanding, and expert-validated gains in narrative quality compared with conventional LLM-based reading. Our contributions lie in designing a multi-agent framework for transforming academic papers into pedagogically optimized slides and introducing interactive customization for personalized learning.